prikaz prve stranice dokumenta Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes
  Download
PDF 1.57 MB
Scientific paper - Original scientific paper
Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes
Biology, 11 (2022), 6; 917. https://doi.org/10.3390/biology11060917
Attia, MennattAllah Hassan; Kholief, Marwa A.; Zaghloul, Nancy M.; Kružić, Ivana; Anđelinović, Šimun; Bašić, Željana; Jerković, Ivan

Cite this document

Attia, M. H., Kholief, M. A., Zaghloul, N. M., Kružić, I., Anđelinović, Š., Bašić, Ž. & Jerković, I. (2022). Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes. Biology, 11. (6). doi: 10.3390/biology11060917

Attia, MennattAllah Hassan, et al. "Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes." Biology, vol. 11, no. 6, 2022. https://doi.org/10.3390/biology11060917

Attia, MennattAllah Hassan, Marwa A. Kholief, Nancy M. Zaghloul, Ivana Kružić, Šimun Anđelinović, Željana Bašić and Ivan Jerković. "Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes." Biology 11, no. 6 (2022). https://doi.org/10.3390/biology11060917

Attia, M. H., et al. (2022) 'Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes', Biology, 11(6). doi: 10.3390/biology11060917

Attia MH, Kholief MA, Zaghloul NM, Kružić I, Anđelinović Š, Bašić Ž, and sur.. Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes. Biology [Internet]. 2022 June 15 [cited 2024 December 26];11(6). doi: 10.3390/biology11060917

M. H. Attia, et al., "Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes", Biology, vol. 11, no. 6, June 2022. [Online]. Available at: https://urn.nsk.hr/urn:nbn:hr:227:784775. [Accessed: 26 December 2024]

Please login to the repository to save this object to your list.
Metadata
Title (english)Efficiency of the Adjusted Binary Classification (ABC) Approach in Osteometric Sex Estimation: A Comparative Study of Different Linear Machine Learning Algorithms and Training Sample Sizes
AuthorMennattAllah Hassan Attia
AuthorMarwa A. Kholief
AuthorNancy M. Zaghloul
AuthorIvana Kružić
AuthorŠimun Anđelinović
AuthorŽeljana Bašić
AuthorIvan Jerković
Author's institutionUniversity of Split
University Department of Forensic Sciences
Scientific / art field,
discipline and subdiscipline		BIOMEDICINE AND HEALTHCARE
Basic Medical Sciences
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Security and Defense Science
Abstract (english)
The adjusted binary classification (ABC) approach was proposed to assure that the binary classification model reaches a particular accuracy level. The present study evaluated the ABC for osteometric sex classification using multiple machine learning (ML) techniques: linear discriminant analysis (LDA), boosted generalized linear model (GLMB), support vector machine (SVM), and logistic regression (LR). We used 13 femoral measurements of 300 individuals from a modern Turkish population sample and split data into two sets: training (n = 240) and testing (n = 60). Then, the five best-performing measurements were selected for training univariate models, while pools of these variables were used for the multivariable models. ML classifier type did not affect the performance of unadjusted models. The accuracy of univariate models was 82–87%, while that of multivariate models was 89–90%. After applying ABC to the crossvalidation set, the accuracy and the positive and negative predictive values for uni- and multivariate models were ≥95%. Sex could be estimated for 28–75% of individuals using univariate models but with an obvious sexing bias, likely caused by different degrees of sexual dimorphism and between-group overlap. However, using multivariate models, we minimized the bias and properly classified 81–87% of individuals. A similar performance was also noted in the testing sample (except for FEB), with accuracies of 96–100%, and a proportion of classified individuals between 30% and 82% in univariate models, and between 90% and 91% in multivariate models. When considering different training sample sizes, we demonstrated that LR was the most sensitive with limited sample sizes (n < 150), while GLMB was the most stable classifier.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Journal titleBiology
Numberingvol. 11, no. 6, 917
e-ISSN2079-7737
DOIhttps://doi.org/10.3390/biology11060917
URN:NBNurn:nbn:hr:227:784775
Publication2022-06-15
Document URLhttps://www.mdpi.com/2079-7737/11/6/917
Type of resourceText
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2024-06-10 12:27:47